初始化项目，由ModelHub XC社区提供模型

Model: amd/ReasonLite-0.6B-Turbo Source: Original Platform
2026-07-31 12:16:20 +08:00
commit 4740fbc4aa
13 changed files with 152252 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/304
+++ b/304
@@ -0,0 +1,304 @@
+ReasonLite [Open RAIL-D] 
+
+Licensed Artifact(s):
+
+-   Data
+
+Section I: PREAMBLE
+
+BY ACCESSING, DOWNLOADING, INSTALLING, OR USING THE ARTIFACT, YOU AGREE
+TO BE BOUND BY THIS LICENSE. IF YOU DO NOT AGREE TO ALL OF THE TERMS AND
+CONDITIONS OF THIS LICENSE, DO NOT ACCESS, DOWNLOAD, INSTALL, OR USE THE
+ARTIFACT.
+
+1. Definitions
+
+(a) “Application” refers to a sequence of instructions or statements
+    written in machine code language, including object code (that is the
+    product of a compiler), binary code (data using a two-symbol system)
+    or an intermediate language (such as register transfer language).
+
+(b) “Artifact” refers to a software application (in either binary or
+    source code format), Data, Model, and/or Source Code, in accordance
+    with what is specified above as the “Licensed Artifact”.
+
+(c) “Contribution” means any work, including any modifications or
+    additions to an Artifact, that is intentionally submitted to
+    Licensor for inclusion or incorporation in the Artifact directly or
+    indirectly by the rights owner. For the purposes of this definition,
+    “submitted” means any form of electronic, verbal, or written
+    communication sent to the Licensor or its representatives, including
+    but not limited to communication on electronic mailing lists, source
+    code control systems, and issue tracking systems that are managed
+    by, or on behalf of, the Licensor for the purpose of discussing,
+    sharing and improving the Artifact, but excluding communication that
+    is conspicuously marked or otherwise designated in writing by the
+    contributor as “Not a Contribution.”
+
+(d) “Contributor” means Licensor or any other individual or legal entity
+    that creates or owns a Contribution that is added to or incorporated
+    into an Artifact or its Derivative.
+
+(e) “Data” means a collection of information and/or content extracted
+    from the dataset used with a given Model, including to train,
+    pretrain, or otherwise evaluate the Model. 
+
+(f) “Derivative” means a work derived from or based upon an Artifact,
+    and includes all modified versions of such Artifact.
+
+(g) “Distribution” means any transmission, reproduction, publication or
+    other sharing of an Artifact or Derivative to a Third Party,
+    including providing a hosted service incorporating the Artifact,
+    which is made available by electronic or other remote means -
+    e.g. API-based or web access.
+
+(h) “Harm” includes but is not limited to physical, mental,
+    psychological, financial and reputational damage, pain, or loss.
+
+(i) “License” means the terms and conditions for use, reproduction, and
+    Distribution as defined in this document.
+
+(j) “Licensor” means the rights owner (by virtue of creation or
+    documented transfer of ownership) or entity authorized by the rights
+    owner (e.g., exclusive licensee) that is granting the rights in this
+    License.
+
+(k) “Model” means any machine-learning based assembly or assemblies
+    (including checkpoints), consisting of learnt weights, parameters
+    (including optimizer states), corresponding to the model
+    architecture as embodied in the Source Code.
+
+(l) “Output” means the results of operating a Model as embodied in
+    informational content resulting therefrom.
+
+(m) “Source Code” means any collection of text written using
+    human-readable programming language, including the code and scripts
+    used to define, run, load, benchmark or evaluate a Model or any
+    component thereof, and/or used to prepare data for training or
+    evaluation, if any. Source Code includes any accompanying
+    documentation, tutorials, examples, etc, if any. For clarity, the
+    term “Source Code” as used in this License includes any and all
+    Derivatives of such Source Code.
+
+(n) “Third Parties” means individuals or legal entities that are not
+    under common control with Licensor or You.
+
+(o) “Use” includes accessing, using, copying, modifying, and/or
+    distributing an Artifact; in connection with a Model as Artifact,
+    Use also includes creating content, fine-tuning, updating, running,
+    training, evaluating and/or re-parametrizing such Model.
+
+(p) “You” (or “Your”) means an individual or legal entity receiving and
+    exercising permissions granted by this License and/or making use of
+    the Artifact for permitted purposes and in any permitted field of
+    use, including usage of the Artifact in an end-use application -
+    e.g. chatbot, translator, image generator, etc.
+
+Section II: INTELLECTUAL PROPERTY RIGHTS
+
+Both copyright and patent grants may apply to the Artifact. The Artifact
+is subject to additional terms and conditions as described in Section III
+below. 
+
+2. Grant of Copyright License. Conditioned upon compliance with Section
+III below and subject to the terms and conditions of this License, each
+Contributor hereby grants to You a worldwide, non-exclusive, royalty-free copyright license to
+reproduce, use, publicly display, publicly perform, sublicense, and
+distribute the Artifact and Derivatives thereof.
+
+3. Grant of Patent License. Conditioned upon compliance with Section III
+below and subject to the terms and conditions of this License, and only
+where and as applicable, each Contributor hereby grants to You a worldwide, non-exclusive,
+royalty-free, irrevocable (except as stated in this paragraph) patent
+license to make, have made, use, sell, offer to sell, import, and
+otherwise transfer the Artifact where such license applies only to those
+patent claims licensable by such Contributor that are necessarily
+infringed by their Contribution(s) alone or by combination of their
+Contribution(s) with the Artifact to which such Contribution(s) was
+submitted. If You institute patent litigation against any entity
+(including a cross-claim or counterclaim in a lawsuit) alleging that the
+Artifact and/or a Contribution incorporated within the Artifact
+constitutes direct or contributory patent infringement, then any patent
+licenses granted to You under this License in connection with the
+Artifact shall terminate as of the date such litigation is asserted or
+filed.
+
+Licensor and Contributor each have the right to grant the licenses
+above.
+
+Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
+
+4. Use-based restrictions. The restrictions set forth in Attachment A
+are mandatory Use-based restrictions. Therefore You may not Use the
+Artifact in violation of such restrictions. You may Use the Artifact
+only subject to this License. You shall require all of Your users who
+use the Artifact or its Derivative to comply with the terms of this
+paragraph.
+
+5. The Output You Generate with a Model (as Artifact). Except as set
+forth herein, Licensor claims no rights in the Output You generate. You
+are accountable for the Output You generate and its subsequent uses. No
+use of the Output may contravene any provision as stated in this
+License.
+
+6. Distribution and Redistribution. You may host for Third Party remote
+access purposes (e.g. software-as-a-service), reproduce and distribute
+copies of the Artifact or its Derivatives in any medium, with or without
+modifications, provided that You meet the following conditions:
+
+6.1.  Use-based restrictions in paragraph 4 MUST be included as a
+      condition precedent to effect any type of legal agreement (e.g. a
+      license) governing the use and/or distribution of the Artifact or
+      its Derivatives, and You shall give such notice to any subsequent
+      Third Party recipients;
+6.2.  You shall give any Third Party recipients of the Artifact or its
+      Derivatives a copy of this License;
+6.3.  You shall cause any modified files to carry prominent notices
+      stating that You changed the files;
+6.4.  You shall retain all copyright, patent, trademark, and attribution
+      notices excluding those notices that do not pertain to any part of
+      the Artifact or its Derivatives.
+
+You may add Your own copyright statement to Your modifications and may
+provide additional or different license terms and conditions with
+respect to paragraph 6.1., to govern the use, reproduction, or
+Distribution of Your modifications, or for any Derivative, provided that
+Your use, reproduction, and Distribution of the Artifact or its
+Derivative otherwise complies with the conditions stated in this
+License. In other words, the Use-based restrictions in Attachment A form
+the minimum set of terms for You to license to Third Parties any
+Artifact or its Derivative, but You may add more restrictive terms if
+You deem it necessary.
+
+Section IV: OTHER PROVISIONS
+
+7. Updates and Runtime Restrictions. To the maximum extent permitted by
+law, Licensor reserves the right to restrict (remotely or otherwise)
+usage of the Artifact in violation of this License or update the
+Artifact through electronic means.
+
+8. Trademarks and Related. Nothing in this License permits You to make
+use of Licensors’ trademarks, trade names, logos or to otherwise suggest
+endorsement or misrepresent the relationship between the parties; and
+any rights not expressly granted herein are reserved by the Licensors.
+
+9. Disclaimer of Warranty. Unless required by applicable law or agreed
+to in writing, Licensor provides the Artifact (and each Contributor
+provides its Contributions) on an “AS IS” BASIS, WITHOUT WARRANTIES OR
+CONDITIONS OF ANY KIND, either express or implied, including, without
+limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT,
+MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely
+responsible for determining the appropriateness of using the Artifact,
+and assume any risks associated with Your exercise of permissions under
+this License.
+
+10. Limitation of Liability. In no event and under no legal theory,
+whether in tort (including negligence), contract, or otherwise, unless
+required by applicable law (such as deliberate and grossly negligent
+acts) or agreed to in writing, shall any Contributor be liable to You
+for damages, including any direct, indirect, special, incidental, or
+consequential damages of any character arising as a result of this
+License or out of the use or inability to use the Artifact (including
+but not limited to damages for loss of goodwill, work stoppage, computer
+failure or malfunction, or any and all other commercial damages or
+losses), even if such Contributor has been advised of the possibility of
+such damages.
+
+11. If any provision of this License is held to be invalid, illegal or
+unenforceable, the remaining provisions shall be unaffected thereby and
+remain valid as if such provision had not been set forth herein.
+
+12. Term and Termination. The term of this License will commence upon
+the earlier of Your (a) acceptance of this License or (b) accessing the
+Artifact; and will continue in full force and effect until terminated in
+accordance with the terms and conditions herein. Licensor may terminate
+this License if You are in breach of any term or condition of this
+License. Upon termination of this License, all licenses granted to You
+will terminate and You must promptly delete and cease use of the
+Artifact. Sections 1, 7, 8, 9, 10, 11, and 12 survive termination of
+this License.
+
+END OF TERMS AND CONDITIONS
+
+Attachment A
+
+AMD Responsible AI Use Policy
+
+AMD is committed to the responsible use of its Artificial Intelligence
+(AI) products and technologies (“AMD AI”).  AMD AI may include
+artificial intelligence or machine learning technologies that use
+algorithms to analyze data and generate output using predictions based
+on patterns in data.  This policy explains the uses that AMD
+specifically prohibits.
+
+If you use any AMD AI, you are agreeing to use the AMD AI in compliance
+with applicable laws and not for any of the following prohibited uses.
+
+Prohibited Uses:
+
+1) No Illegal Acts.  Do not use AMD AI in violation of any applicable
+national, state, local, or other jurisdictional law, rule, regulation,
+or sanction.
+
+2) No Explicit Content.  Do not use AMD AI to submit (as input),
+generate, or disseminate content depicting violent or sexually explicit
+content or to create sexual chatbots.
+
+3) No Harm.  Do not use AMD AI for any potentially harmful uses,
+   including fraud, deception, discrimination, abuse, or harassment,
+   including the following:
+
+   a) Harm or abuse of a minor, including grooming and child sexual
+      exploitation.
+
+   b) Impersonation of human beings for purposes of deception.
+
+   c) Generation or dissemination of information you know to be false
+      for the purpose of harming others.
+
+   d) Intentionally defame, disparage, or otherwise harass others.
+
+   e) Intentionally attempting to materially distort the behavior of a
+      person in a manner that causes or is likely to cause that person
+      or another person physical or psychological harm.
+
+   f) Providing medical advice or interpretation of medical results that
+      is intended to be a substitute for professional medical advice,
+      diagnosis, or treatment.
+
+   g) Engaging in the unlawful or unauthorized practice of any
+      profession, including financial, legal, medical, health, or
+      related professional practices.
+
+   h) Judgment of, discrimination against, or harm to individuals or
+      groups based on legally protected characteristics or categories,
+      online or offline social behavior, or known or predicted personal
+      or personality characteristics, including any of the foregoing
+      uses in social credit systems.
+
+4) No High-Risk Activity.  Do not use AMD AI in any high-risk activities
+ or applications that create a risk of personal injury, death, or
+severe property or environmental damage, including in weapons or
+military applications.
+
+5) No Personal Information.  Do not use AMD AI to collect, process, or
+disclose personal data, including heath or sensitive personal
+information, without the necessary rights or consents.
+
+6) No Infringement.  Do not use AMD AI to generate or disseminate any
+information that infringes upon or misappropriates the intellectual
+property rights of others, including copyright, trademark, patent, and
+trade secret rights, rights to privacy, and publicity rights.
+
+7) No Malware.  Do not use AMD AI to generate or disseminate malware or
+any other content to be used for the purpose of facilitating unpermitted
+access to, or use of, computer systems or data.
+
+8) No Obfuscation.  Do not inappropriately obfuscate or fail to disclose
+to end users the presence of AI in any application in which AMD AI is
+deployed, along with any known risks or dangers of using AI without
+appropriate safeguards, oversight and human control.
+
+9) No Reliance.  Do not rely on any information generated using AMD AI
+without assessing it for accuracy, potential for harm, or other specific
+risks applicable to the use case.
--- a/README.md
+++ b/README.md
@@ -0,0 +1,93 @@
+---
+license: openrail
+datasets:
+- amd/ReasonLite-Dataset
+---
+
+
+
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/66a056d0229269a861ac1245/9xXXms4ub9dzbcsN1IGqq.png" alt="ReasonLite" width="200">
+</p>
+
+<p align="center">
+<a href="https://github.com/AMD-AGI/ReasonLite"><b>GitHub</b></a> |
+<a href="https://huggingface.co/datasets/amd/ReasonLite-Dataset"><b>Dataset</b></a> |
+<a href="https://www.amd.com/en/developer/resources/technical-articles/2026/introducing-reasonlite-0-6b.html"><b>Blog</b></a> 
+
+</p>
+
+
+**ReasonLite is an ultra-lightweight math reasoning model.** With only 0.6B parameters, it leverages **high-quality data distillation** to achieve performance comparable to models over 10× its size, such as Qwen3-8B, **reaching 75.2 on AIME24 and extending the scaling law of small models.**
+
+* 🔥 **Best-performing 0.6B math reasoning model**
+* 🔓 Fully open-source — weights, scripts, datasets, synthesis pipeline
+* ⚙️ Distilled in two stages to balance **efficiency** and **high performance**, using **6.1M** high-quality samples.
+
+
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/66a056d0229269a861ac1245/MCLe1ttoeHc_8181gKRPy.png"" alt="ReasonLite" height="500">
+</p>
+
+---
+
+# 🚀 Model
+
+The model is trained in **two progressive distillation stages**.
+First, short-CoT data is used to distill **Qwen3-0.6B** into **ReasonLite-0.6B-Turbo**, improving **AIME24 accuracy from 11.0 → 57.1**.
+Then, long-CoT data is used to obtain **ReasonLite-0.6B**, further boosting accuracy to **75.2**.
+
+| Model                     | Description                                   | AIME24 | Link |
+| ------------------------- | ----------------------------------------------| ------ | ---- |
+| **amd/ReasonLite-0.6B-Turbo** | Short CoT balancing performance and efficiency | 57.1  | [🤗 HuggingFace](https://huggingface.co/amd/ReasonLite-0.6B-Turbo) |
+| **amd/ReasonLite-0.6B**       | Long CoT for high performance                  | 75.2  | [🤗 HuggingFace](https://huggingface.co/amd/ReasonLite-0.6B) |
+
+---
+
+# 📊 Evaluation Results
+
+**Metrics**
+
+* **avg@16** — average accuracy from 16 sampled answers
+* **pass@8** — probability at least one correct answer appears among 8 samples
+
+| Model                     | Parameters | AMC23 avg@16 | AMC23 pass@8 | AIME25 avg@16 | AIME25 pass@8 | AIME24 avg@16 | AIME24 pass@8 |
+|---------------------------|------------|-------------|-------------|---------------|---------------|---------------|---------------|
+| Qwen2.5-14B               | 14B        | 58.3        | 82.3        | 12.3          | 32.3          | 12.7          | 32.4          |
+| Deepseek-qwen-14B         | 14B        | 93.9        | 98.7        | 50.2          | 71.0          | 65.0          | 83.0          |
+| Qwen3-0.6B                | 0.6B       | 52.7        | 85.0        | 16.0          | 33.0          | 11.0          | 31.5          |
+| Qwen3-1.7B                | 1.7B       | 83.4        | 96.3        | 36.0          | 55.1          | 47.3          | 73.9          |
+| Qwen3-4B                  | 4B         | 96.1        | 100         | 63.5          | 85.4          | 72.7          | 85.1          |
+| Qwen3-8B                  | 8B         | 94.8        | 100         | 68.3          | 84.2          | 74.6          | 85.0          |
+| Qwen3-14B                 | 14B        | 98.6        | 98.7        | 71.5          | 84.1          | 78.3          | 88.4          |
+| DeepscaleR-1.5B           | 1.5B       | 83.8        | 95.0        | 29.0          | 48.9          | 40.4          | 69.0          |
+| POLARIS-1.7B-Preview      | 1.7B       | 92.2        | 97.4        | 52.3          | 80.2          | 65.0          | 76.7          |
+| OpenMath-Nemotron-1.5B    | 1.5B       | 88.8        | 96.7        | 39.8          | 65.8          | 61.5          | 81.3          |
+| ReasonLite-0.6B-Turbo     | 0.6B       | 81.6        | 99.3        | 42.7          | 69.2          | 57.1          | 79.6          |
+| **ReasonLite-0.6B**       | **0.6B**   | **95.2**    | **100**     | **62.9**      | **84.1**      | **75.2**      | **90.2**      |
+
+
+---
+
+# 📚 Dataset
+
+We collected 343K math problems from Polaris and OpenMathReasoning. Using GPT-OSS as the teacher, we generated 9.1M raw answers under medium and high reasoning modes. We then produced pseudo-labels via majority voting, and finally retained 6.1M samples.
+
+| Dataset                | Description | Size | Link |
+| ---------------------- | ------      |---- | ---- |
+| **amd/ReasonLite-Dataset** | Short CoT | 4.3M  | [🤗 HuggingFace](https://huggingface.co/datasets/amd/ReasonLite-Dataset/viewer/default/medium) |
+| **amd/ReasonLite-Dataset**  | Long Cot | 1.8M  | [🤗 HuggingFace](https://huggingface.co/datasets/amd/ReasonLite-Dataset/viewer/default/high) |
+
+---
+
+# 📌 Citation
+
+```bibtex
+@misc{reasonlite2025,
+  title    = {ReasonLite: An Ultra-Lightweight 0.6B Reasoning Model},
+  author   = {An, Zihao and Chen, Chushi and Liu, Ziqiong and Li, Dong and Barsoum, Emad},
+  year     = {2025},
+  url      = {https://github.com/AMD-AGI/ReasonLite},
+  note     = {Open-source project}
+}
+```
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.3"
+}
--- a/merges.txt
+++ b/merges.txt
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92006675ff90181595ae5fe1ecda61c9daba1e74b6ad35aeb88f85f17fb0cac
+size 1503300328
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": "<|im_end|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/vocab.json
+++ b/vocab.json